Backport PR #1303 on branch 2.x (Add default_completions_model trait) (#1306)

* Update learn.py

* Add `default_completions_model` trait (#1303)

* Updating inline completions config fields from prespecified custom config file

* Update extension.py

(cherry picked from commit a82eecc)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update extension.py

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: srdas

docs/source/users/index.md

@@ -1087,6 +1087,11 @@ Specify default embedding model
 jupyter lab --AiExtension.default_embeddings_model=bedrock:amazon.titan-embed-text-v1
 ```
 
+Specify default completions model
+```bash
+jupyter lab --AiExtension.default_completions_model=bedrock-chat:anthropic.claude-v2
+```
+
 Specify default API keys
 ```bash
 jupyter lab --AiExtension.default_api_keys={'OPENAI_API_KEY': 'sk-abcd'}

packages/jupyter-ai/jupyter_ai/extension.py

@@ -151,6 +151,16 @@ class AiExtension(ExtensionApp):
         config=True,
     )
 
+    default_completions_model = Unicode(
+        default_value=None,
+        allow_none=True,
+        help="""
+        Default completions model to use, as string in the format
+        <provider-id>:<model-id>, defaults to None.
+        """,
+        config=True,
+    )
+
     default_api_keys = Dict(
         key_trait=Unicode(),
         value_trait=Unicode(),
@@ -214,6 +224,7 @@ def initialize_settings(self):
         defaults = {
             "model_provider_id": self.default_language_model,
             "embeddings_provider_id": self.default_embeddings_model,
+            "completions_model_provider_id": self.default_completions_model,
             "api_keys": self.default_api_keys,
             "fields": self.model_parameters,
             "embeddings_fields": self.model_parameters,